Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 963 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1260044 (The Pile)

Max Activating Token Index: 277

Text #1

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.2220. Min Act: -0.0000

Data Index: 519584 (The Pile)

Max Activating Token Index: 129

Text #2

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.1298. Min Act: -0.0000

Data Index: 164188 (The Pile)

Max Activating Token Index: 862

Text #3

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0556. Min Act: -0.0000

Data Index: 265490 (The Pile)

Max Activating Token Index: 422

Text #4

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0765. Min Act: -0.0000

Data Index: 556555 (The Pile)

Max Activating Token Index: 189

Text #5

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9158. Min Act: -0.0000

Data Index: 840081 (The Pile)

Max Activating Token Index: 953

Text #6

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1757413 (The Pile)

Max Activating Token Index: 481

Text #7

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9883. Min Act: -0.0000

Data Index: 1863320 (The Pile)

Max Activating Token Index: 513

Text #8

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9835. Min Act: -0.0000

Data Index: 158115 (The Pile)

Max Activating Token Index: 650

Text #9

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1148037 (The Pile)

Max Activating Token Index: 434

Text #10

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9551. Min Act: -0.0000

Data Index: 1951762 (The Pile)

Max Activating Token Index: 47

Text #11

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9420. Min Act: 0.0000

Data Index: 1031752 (The Pile)

Max Activating Token Index: 41

Text #12

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1433165 (The Pile)

Max Activating Token Index: 896

Text #13

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9312. Min Act: 0.0001

Data Index: 390131 (The Pile)

Max Activating Token Index: 67

Text #14

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9342. Min Act: 0.0000

Data Index: 129624 (The Pile)

Max Activating Token Index: 985

Text #15

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9787. Min Act: -0.0000

Data Index: 554471 (The Pile)

Max Activating Token Index: 1005

Text #16

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1177092 (The Pile)

Max Activating Token Index: 326

Text #17

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9600. Min Act: -0.0000

Data Index: 713738 (The Pile)

Max Activating Token Index: 499

Text #18

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.8759. Min Act: 0.0000

Data Index: 1520940 (The Pile)

Max Activating Token Index: 238

Text #19

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1791449 (The Pile)

Max Activating Token Index: 317